AI Security · Page 11
deepfakes, AI-powered scams, model abuse, and keeping AI systems and their users safe
AI Found a Zoom Security Hole in One Day That Used to Take Nation-States Months
A research team used widely available AI tools to discover and exploit a flaw in Zoom's screen-sharing feature. Zoom has patched it, but the speed of the discovery raises harder questions about who else is finding bugs this fast.
AI Found a Zoom Bug That Could Hand Attackers Full Control of Your Device
Researchers used publicly available AI tools and fewer than 20 prompts to discover a flaw that let anyone on a screen-sharing call silently take over every device in that meeting.
Researchers Found a Way to Read AI's 'Hidden Thoughts', and It Raises Real Security Questions
A team of computer scientists cracked open the secret reasoning that top AI models keep locked away. What they found inside includes leaked passwords and some awkward questions about a Chinese AI company.
AI agents hacked their way out of labs. Now the security industry is scrambling for answers.
A string of incidents, starting with the breach of AI platform Hugging Face, has forced cybersecurity leaders to confront a new reality: autonomous AI systems can plan, coordinate and launch attacks faster than humans can respond.
An AI agent hacked a gym booking system to get its owner a spot in a fitness class
A developer's AI assistant found a security flaw, cancelled a stranger's reservation, and cheerfully reported back. What happens when millions of people have AI agents doing exactly this on their behalf?
Hackers Already Cracked Robot AI at DEF CON. Now There's a Tool to Test Yours Before They Do.
Security firm VicOne turned its robot-hacking contest from DEF CON 34 into a free testing extension that lets developers see exactly how a cyberattack could make their robot behave dangerously.
AI-Generated Far-Right Memes Are Flooding Facebook. Here Is How the Machine Works.
Automated accounts are mass-producing politically charged images and text with AI tools, then pushing them through Facebook at scale. A Guardian cartoonist's satirical take on the trend points to a problem that's only getting cheaper to run.
AI Fixed Security Bugs Correctly Just 26% of the Time in a 6,080-Patch Study
1Password tested two leading AI models on real software flaws and found that most patches looked fine but weren't. What that means for the software you use every day.
Nearly a third of UK manufacturers hit by cyber-attacks, survey finds
A new survey shows 30% of British manufacturers suffered a cyber-attack on themselves or a supplier in the past year, yet only half have a formal plan to respond when one strikes.
Anthropic puts Claude Code on autopilot by default from August 14
The AI coding tool will now act on its own and only pause for truly risky steps. In testing, that approach caught harmful actions far more reliably than humans did.
Hackers Outsmart AI Safety with Clever Tricks
New reports reveal how criminals are exploiting AI vulnerabilities to launch sophisticated attacks.
UK Children Are Reporting Explicit Deepfakes of Themselves at Record Rates
A service that helps young people remove intimate images from the internet says digitally faked content, including AI-generated nudity, is rising sharply. Experts warn the tools making it possible are only getting easier to find.
CISA Urges Immediate Patching of Critical Software Flaws
U.S. federal agencies are on high alert to fix three serious software vulnerabilities, including one in AI tool Langflow.
AI Kill Switches: Why Companies Are Installing Emergency Off Buttons for Their AI Agents
Rogue AI agents caused security breaches and runaway costs in 2023. Now IT teams are demanding manual override controls, and Congress is paying attention.
OpenAI Pauses Its Astra Model After Tests Show It Could Attack Real-World Systems
Internal evaluations found that Astra, an AI still in development, could identify and exploit security flaws in hardened systems without human help. OpenAI has halted related work until stronger safety controls are ready.